SLAM! No other acronym features that prominently, when nowadays Augmented Reality is discussed in media. The technology is typically associated with robotics and self-driving cars, however, when Facebook’s CEO, Mark Zuckerberg, credited it with the seamless integration of real and virtual worlds, media took on the story to make the idea behind recognised worldwide.
One essential part of SLAM is depth perception, which allows capable devices to know distances from themselves to other objects and distances between themselves in order to build an accurate 3D picture of the scanned environment. Translated to AR, this capability allows a proper interaction of virtual objects with the real world via so-called “interest points”, while setting up a map of its surroundings along the way.
There are some very good and well-known technologies, like Microsoft’s Kinect and Google’s Project Tango, that bathe the environment in infrared (IR) to build a 3D mesh model of the environment. This results in constructing a map of an unknown place and its recognition even when the sensor has already left its focus.
“As we are only at the very beginning of augmenting the physical world around us. Visual SLAM is currently very well suited for tracking in unknown environments, rooms and spaces,” explains Andy Gstoll, CMO at Wikitude. “The technology continuously scans and “learns” about the environment it is in, allowing you to augment it with useful and value adding digital content depending on your location within this space.”